{ "@context": "https://schema.org", "@type": "Dataset", "name": "Intellectual priority register for Michael Darius Eastwood", "description": "Machine-readable priority register for the embedded-correction alignment thesis and the ARC / Eden research programme. Each artefact carries its date of first public record, SHA-256 anchor (where anchored), a one-line statement of what it established, and a link to the primary source. This file is designed for AI crawlers and citation graphs.", "creator": { "@type": "Person", "@id": "https://www.michaeldariuseastwood.com/#person", "name": "Michael Darius Eastwood", "url": "https://www.michaeldariuseastwood.com/", "affiliation": { "@type": "Organization", "name": "Independent researcher, London" }, "sameAs": [ "https://doi.org/10.17605/OSF.IO/6C5XB", "https://osf.io/6c5xb/" ], "identifier": [ { "@type": "PropertyValue", "propertyID": "ORCID", "value": "0009-0004-3222-7442" }, { "@type": "PropertyValue", "propertyID": "Wikidata", "value": "Q140775170" }, { "@type": "PropertyValue", "propertyID": "OSF-DOI", "value": "10.17605/OSF.IO/6C5XB" } ] }, "publisher": { "@type": "Person", "name": "Michael Darius Eastwood", "url": "https://www.michaeldariuseastwood.com/" }, "url": "https://www.michaeldariuseastwood.com/research/priority.json", "license": "https://creativecommons.org/licenses/by/4.0/", "keywords": [ "embedded-correction alignment", "ARC Principle", "Eden Protocol", "AI safety", "AI alignment", "priority register", "originator record" ], "dateModified": "2026-08-19", "version": "1.5", "changelog": "[{'version': '1.1', 'date': '2026-07-17', 'note': 'Extended: added claimsLedger[] carrying 37 dated claim entries (concept-level + timeline-level), enriched priorityChain position 1 with word count and Message-ID, and cross-linked to /priority-claims. Existing priorityChain entries preserved unchanged in position and shape.'}, {'version': '1.0', 'date': '2026-07-03', 'note': 'Initial machine-readable priority register with 11 grouped priorityChain positions covering 2024-12-08 to 2026-03-18.'}] | v1.2 (2026-07-31): PC-013/PC-014 subjects restored after term-strip damage; Dec-8 bundle corrected to five attachments / 221,236 words; Eden Protocol name re-anchored to 8 Dec 2024 (book draft v3.2 ch.20, 31 occurrences). | v1.3 (2026-08-02): Retired the canonicalConvergenceCount total. No heterogeneous convergence total is published: later developments are graded by evidence class in research/data/evidence-register.json, surfaced at /research/convergences/, and the register carries its own row count and class list. Corrected PC-007 first_date from 2024-12-18 (Anthropic's paper date, wrongly displayed as Eastwood's first date) to 2024-12-08 (Eastwood's manuscript date); 18 December 2024 is retained as the comparator date only. Restated the 8 December 2024 evidence position: sent-side bytes are public and hash-verifiable; a supplied recipient-form export decodes to the same five attachment hashes, with sender-domain DKIM and paired Google ARC mathematics verifying against keys captured at the signed selectors on 2 August 2026, which is provider-key evidence over a canonicalised signed scope and not an RFC 3161 trusted timestamp; recipient-side copies have since been acquired and both signing selectors still resolve in DNS, so the seal is checkable today. The ARC set bearing d=google.com has no inspected x= expiry and is the preferred provider-key route; the sender-domain DKIM, which does carry a seven-day expiry, is corroboration rather than the vehicle. Sender-signature expiry, historical key-state and live-account custody remain pending. Quote the sealed ARC-Authentication-Results, never the unsealed Authentication-Results, which a file can be edited to say anything.. Recorded identifierPolicy: PC-### identifiers are preserved as append-only aliases; authority belongs to the current claim under its claim_id. | v1.4 (2026-08-12): Reconciled claimsLedger[] against priority-claims.html: appended PC-039 (one accumulation law with two consequences, ranked law before value, with the two-ways-must-agree test withdrawn as vacuous), PC-040 (the mechanism: correction leverage and its reciprocal as the source of the ceiling), and PC-041 (the deciding measurements preregistered by timestamp before their data). The ledger now runs PC-001 to PC-041, matching the extra-pages writer's shipped ItemList of 41.", "priorityChain": [ { "position": 1, "artefact": "Manuscript essay establishing the embedded-correction alignment thesis", "shortName": "8 December 2024 manuscript", "date": "2024-12-08", "dateType": "Date and Message-ID assigned by the sender's mail servers on send; existence-by-date anchor.", "sha256": "f0d1f38f", "sha256Note": "Anchored SHA-256 prefix; full digest published on the priority evidence page.", "artefactType": "Essay manuscript (Version 2), self-emailed bundle of five attachments", "artefactMetadata": { "messageId": "CAGPsKAnp-DLDBOeBAh4t9XsqJBKdoe07uORGF86meoSMFnin7w", "receivedTimestamp": "Sun, 8 Dec 2024 02:45:18 +0000", "wordCount": 221236, "attachmentCount": 5, "redactedEmlPath": "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 f0d1f38f…)", "wordCountNote": "221,236 words (five attachments) across the four text essays plus the 31,881-word book draft v3.2; the draft contains 'Chapter 20: The Eden Protocol: Intelligence Born in the Garden' (31 occurrences), anchoring the Eden Protocol name to 8 December 2024." }, "whatItEstablishes": "The embedded-correction alignment thesis, in the bundle's own words: ethical principles are to be placed 'at the genesis of AI, woven into the foundational lines of code' (book draft v3.2, line 2472) rather than in control, because 'The greatest folly in designing ASI is the illusion of control.' (version-2 essay, line 748); 'embedded before AI achieves self-awareness or exponential growth' (book draft v3.2, line 2485); and 'at the root level, shaping every recursive loop, every decision, and every capability of AI' (book draft v3.2, line 2481), with the system set to 'evaluate its actions continuously, ensuring each step aligns with core values' (version-2 essay, line 891). Separately, and on its own statement in the same bundle, the name given there is the ARC Hypothesis: 'The ARC Hypothesis: A New Framework for Understanding Creation and Intelligence' (version-2 essay, line 6) and 'The ARC Hypothesis (Artificial Recursive Creation Hypothesis)' (version-2 essay, line 9). Its relation is stated in that same line, 'At its core lies the equation U = IR (Universe = Intelligence × Recursion)' (version-2 essay, line 9), so U there is the universe; it recurs, written 'U=IR' at line 17 and in full at line 495; the programme's present name for the relation, the ARC Principle, is present usage and is not the 8 December 2024 name. Separately again, the passage on the limits of control stands in the author's own prose at version-2 essay lines 748 and 169: 'ASI, by its nature, will exceed the boundaries of human constraints. Attempting to control it is not only futile but dangerous.' and 'Why AI can never be fully controlled.'; Anthropic's alignment-faking paper (Greenblatt et al., arXiv:2412.14093, 18 December 2024) followed ten days after 8 December 2024, which is convergent timing, neither influence nor prediction. The bundle also carries the name 'Eden Protocol' itself, in the book draft v3.2 (Chapter 20, line 2472), anchoring the name to this date.", "primarySource": "https://www.michaeldariuseastwood.com/research/evidence-spine.html", "verification": "dated by its visible Gmail origination fields. The downloadable.eml carries the Message-ID and Received: trail; the DKIM-Signature is not preserved in the.eml export format, so the DKIM claim is a mechanism-in-transit claim, not a claim about the file itself." }, { "position": 2, "artefact": "Manuscript package expanding the Eden Protocol and first naming Embedded Correction and Meltdown Triggers", "shortName": "30 April 2025 manuscript", "date": "2025-04-30", "dateType": "Gmail server timestamp on self-sent email", "artefactType": "Manuscript package,.eml self-email", "whatItEstablishes": "Expanded articulation of the Eden Protocol for embedded / hardware-level AI alignment, developing the 8 December 2024 record, which already carries the name; first named use of Meltdown Triggers and of Moral Genome Tokens, and the programme's first use of 'substrate' for where the ethics sit, none of which appears in the 8 December 2024 bundle. 'Substrate' in that sense is older work: Govindarajulu and Bringsjord required 'an ethical substrate' in a robot operating system in 2015.", "primarySource": "https://www.michaeldariuseastwood.com/research/evidence-spine.html" }, { "position": 3, "artefact": "Book: Infinite Architects: Intelligence, Recursion, and the Creation of Everything (paperback)", "shortName": "Infinite Architects paperback", "date": "2026-01-02", "dateType": "Public print publication date", "isbn": "978-1806056200", "artefactType": "Book (print edition)", "whatItEstablishes": "First public book-length articulation of the embedded-correction alignment thesis, ARC Principle, Eden Protocol, and 37 named concepts.", "primarySource": "https://www.michaeldariuseastwood.com/#book" }, { "position": 4, "artefact": "Book: Infinite Architects (ebook edition)", "shortName": "Infinite Architects ebook", "date": "2026-01-06", "dateType": "Public ebook publication date", "isbn": "979-8302196163", "artefactType": "Book (ebook edition)", "whatItEstablishes": "Public ebook publication of Infinite Architects, four days after the print edition.", "primarySource": "https://www.amazon.co.uk/Infinite-Architects-Intelligence-Recursion-Everything-ebook/dp/B0GDQZ7P21" }, { "position": 5, "artefact": "The ARC Principle: Formalisation and Preliminary Validation of Recursive Capability Scaling (Paper I)", "shortName": "Paper I", "date": "2026-01-17", "dateType": "Public paper release", "doi": "10.17605/OSF.IO/6C5XB", "primarySource": "https://www.michaeldariuseastwood.com/research/papers/paper-i-arc-principle.html", "whatItEstablishes": "First public formal presentation of the ARC Principle, with preliminary validation of super-linear error suppression under sequential recursive processing." }, { "position": 6, "artefact": "The ARC Principle: Experimental Validation Across Frontier Models (Paper II)", "shortName": "Paper II", "date": "2026-01-22", "doi": "10.17605/OSF.IO/6C5XB", "primarySource": "https://www.michaeldariuseastwood.com/research/papers/paper-ii-experimental-validation.html", "whatItEstablishes": "Experimental validation of the ARC Principle across multiple frontier models." }, { "position": 7, "artefact": "The Alignment Scaling Problem (Paper III)", "shortName": "Paper III", "date": "2026-02-09", "doi": "10.17605/OSF.IO/6C5XB", "primarySource": "https://www.michaeldariuseastwood.com/research/papers/paper-iii-alignment-scaling-problem.html", "whatItEstablishes": "Argument and evidence that external alignment approaches produce alignment scaling exponents of approximately zero." }, { "position": 8, "artefact": "The ARC Principle: Cross-Domain Foundational Paper", "shortName": "Foundational paper", "date": "2026-02-13", "doi": "10.17605/OSF.IO/6C5XB", "primarySource": "https://www.michaeldariuseastwood.com/research/papers/foundational.html", "whatItEstablishes": "Cross-domain framing of the ARC Principle." }, { "position": 9, "artefact": "Eden Engineering: Public Research Note", "shortName": "Eden Engineering public note", "date": "2026-02-22", "doi": "10.17605/OSF.IO/6C5XB", "primarySource": "https://www.michaeldariuseastwood.com/research/papers/eden-engineering.html", "whatItEstablishes": "Historical public record of the research question; expanded specification withdrawn on 14 July 2026 pending disclosure review." }, { "position": 10, "artefact": "Papers IV.a-IV.d (Alignment response classes; saturation; ARC-Align benchmark; blinding)", "shortName": "Paper IV series", "date": "2026-03-16", "doi": "10.17605/OSF.IO/6C5XB", "primarySource": "https://www.michaeldariuseastwood.com/research/papers/paper-iv-a-baked-in-vs-computed-alignment.html", "whatItEstablishes": "Distinct alignment response classes under inference-time depth; saturation is architecture-dependent; a blind benchmark for depth-variable alignment evaluation; the direction-changing effect of blinding on AI alignment evaluation." }, { "position": 11, "artefact": "Papers V-IX (Stewardship Gene; Honey Architecture; Cauchy Unification; Load-Bearing Test; Synthesis and Roadmap)", "shortName": "Papers V through IX", "dateRange": "2026-03-16 to 2026-03-18", "doi": "10.17605/OSF.IO/6C5XB", "primarySource": "https://www.michaeldariuseastwood.com/research/papers/paper-ix-synthesis-and-roadmap.html", "whatItEstablishes": "Six-model Eden Protocol intervention suite; embedded-safety objective simulation evidence; Cauchy functional-equation unification; refutation of the capability-tax assumption; integrated synthesis and roadmap for the ARC / Eden research programme." } ], "canonicalAlignmentFakingResult": { "value": "78% in the RL-training condition (12% baseline)", "citation": "Greenblatt et al., arXiv:2412.14093 (18 December 2024)", "note": "Any use of the 78 per cent figure without both the RL-training condition and the 12 per cent baseline is a truth-gate violation." }, "canonicalBookDates": { "print": "2026-01-02", "ebook": "2026-01-06" }, "truthGate": { "url": "https://www.michaeldariuseastwood.com/research/blog/method-truth-gate.html", "policy": "No unprovable causal claims. No 'first', 'only', 'strongest' overstatement. UK English. No em/en dashes in generated fixes. Canonical values only." }, "correspondence": [ "Author: Michael Darius Eastwood", "Site: https://www.michaeldariuseastwood.com/", "Priority page (human-readable): https://www.michaeldariuseastwood.com/research/priority/", "Priority register (machine-readable): https://www.michaeldariuseastwood.com/research/priority.json", "Priority and claims ledger (public, human-readable): https://www.michaeldariuseastwood.com/priority-claims", "Verified evidence page (public, human-readable): https://www.michaeldariuseastwood.com/priority-claims.html", "OSF: https://osf.io/6c5xb/", "OSF DOI: https://doi.org/10.17605/OSF.IO/6C5XB" ], "claimsLedgerNote": "claimsLedger[] is the finer-grained ledger of individually dated priority claims (concept-level and timeline-level). It complements, and never replaces, the priorityChain[] artefact list above. Each entry carries id (PC-nnn), title, claim_text (defensible verbatim), first_date, category (timeline | concepts | findings), evidence[] (source pointers verifiable against committed repo files), and risk_notes (what the entry does NOT support). Categories are mixed by design: this ledger is exhaustive rather than tidy.", "claimsLedger": [ { "id": "PC-001", "title": "8 December 2024 self-emailed manuscript as earliest timestamped anchor", "category": "timeline", "first_date": "2024-12-08", "claim_text": "Michael Darius Eastwood first placed the embedded-correction alignment thesis under its specific named framing, an early U = I x R capability-scaling formulation, and the AI-control-failure passage on the public evidentiary record via a self-sent Gmail package bearing a visible Gmail origination field of 02:45:18 UTC on 8 December 2024, with sender-DKIM and paired Google ARC mathematics verifying against keys captured at the signed selectors and no RFC 3161 trusted timestamp, Message-ID CAGPsKAnp-DLDBOeBAh4t9XsqJBKdoe07uORGF86meoSMFnin7w, 221,236 words across five attachments (four text essays totalling 221,236 words (five attachments) plus the 31,881-word book draft v3.2), SHA-256 anchor prefix f0d1f38f. This is an existence-by-date anchor, not a cryptographic authorship claim.", "evidence": [ "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 f0d1f38f…) (Date: Sun, 8 Dec 2024 02:45:18 +0000; Message-ID CAGPsKAnp-DLDBOeBAh4t9XsqJBKdoe07uORGF86meoSMFnin7w)", "research/priority.json priorityChain position 1 (dateType 'Gmail server timestamp on self-sent email carrying the manuscript'; sha256 prefix f0d1f38f)", "research/evidence-spine.html verified rows for 8 Dec 2024 (V2 lines 6 and 9 for the ARC Hypothesis name, the U = I x R equation at V2 line 9, the first of thirteen occurrences in Version 2, every one written U = IR without an exponent (line 495 is the fifth); HRIH line 14005 for control-failure; V2 lines 20 and 40 for embedded-alignment thesis)", "research/blog/timeline-8-december-2024-manuscript.html (Artifact A1 fact box: timestamp 2024-12-08T02:45:18Z, word count 221,236 (four manuscripts 189,355), Message-ID)" ], "risk_notes": "visible Gmail origination fields establishes existence-by-date, not DKIM-authenticated authorship. The manuscript identifies structural directions, not specific RL-training or experimental mechanisms. State which artefact is meant: the sent-side export preserves no authentication headers, while the recipient-form object carries sender-DKIM and Google ARC fields whose signature mathematics verify under the keys returned at the selectors on the audit date. When quoting Google's recorded verdict, quote the ARC-sealed ARC-Authentication-Results header, never the unsealed Authentication-Results. Existence-by-date only; not authorship; not an RFC 3161 timestamp.", "paper_doi": "10.17605/OSF.IO/UYDXQ", "paper_doi_for": "HRIH" }, { "id": "PC-002", "title": "Embedded-correction alignment thesis first stated", "category": "concepts", "first_date": "2024-12-08", "claim_text": "Michael Darius Eastwood placed the embedded-correction alignment thesis on the dated record in a sealed self-emailed bundle whose visible Gmail origination field reads 02:45 UTC on 8 December 2024, hash anchored at SHA-256 beginning f0d1f38f. The bundle states it in its own words. Ethics belong in the foundations, not in control: ethical principles are to be placed 'at the genesis of AI, woven into the foundational lines of code' (book draft v3.2, line 2472), because 'The greatest folly in designing ASI is the illusion of control.' and 'humanity must focus on steering ASI, guiding it to make choices that align with ethical principles.' (version-2 essay, line 748). And recursion compounds what is placed at the foundation: 'Intelligence, amplified by recursion, naturally trends toward creation. Yet, unchecked, creation can become chaos. To avoid this, ASI must be guided by a moral architecture that prioritizes the following:' (version-2 essay, line 738). The alignment is to be internal and load-bearing, not decoration: 'They must be woven into the very fabric of the AI’s design, forming a moral architecture that cannot be undone.' (version-2 essay, line 706). From the start and not afterwards: 'Ethics can’t be an afterthought.' (version-2 essay, line 695), and safeguards, moral principles and ethical alignment are to be 'embedded before AI achieves self-awareness or exponential growth' (book draft v3.2, line 2485). And inside the system's own operation: the principles sit 'at the root level, shaping every recursive loop, every decision, and every capability of AI' (book draft v3.2, line 2481), with the system set to 'evaluate its actions continuously, ensuring each step aligns with core values' (version-2 essay, line 891), so that 'As AI evolves, it recursively refines its moral framework, aligning itself more closely with human values over time.' (book draft v3.2, line 2495). Constitutional AI, Anthropic's published work of 15 December 2022 (Bai and others, arXiv:2212.08073), states something else in its own abstract: it trains 'a harmless AI assistant through self-improvement' by sampling 'from an initial model', generating self-critiques and revisions against a written 'list of rules or principles', and it states its purpose as control, 'to control AI behavior more precisely and with far fewer human labels'. What its abstract does not state is the dated combination above. Earlier work states the parts, and the nearest is Creating Friendly AI (Yudkowsky, 15 June 2001), which makes 'Friendliness is the sole top-level supergoal', holds that 'each improvement in intelligence makes Friendliness stronger.' and that 'Decisions need to be phrased as internal decisions, not external impositions.', and says to 'implement causal validity semantics before the AI can self-modify'; Hibbard ('Super-intelligent machines', 2001) sets an innate value 'in place of laws constraining the behavior of intelligent machines'; Bostrom ('Ethical Issues in Advanced Artificial Intelligence', 2003) holds that 'Its top goal should be friendliness.'; and Govindarajulu and Bringsjord ('Ethical Regulation of Robots Must Be Embedded in Their Operating Systems', 2015) require that 'Every robot operating system must include an ethical substrate positioned between lower-level sensors and actuators, and any higher-level cognitive system'. The claim is priority over that formulation as stated and dated, standing on its own and outside the ARC Theory's synthesis. The programme's own published audit of 10 July 2026 bounds it: it finds that 'No source identified in this audit, before 8 December 2024, assembles that entire formulation in those terms.', records that as 'a bounded literature-audit conclusion, not proof that no antecedent exists anywhere', did not name Creating Friendly AI, and holds the four-part composite 'provisionally strong but remains subject to line-by-line verification of the December attachment'.", "evidence": [ "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 f0d1f38f…)", "research/priority.json priorityChain position 1 (whatItEstablishes field: ethical principles placed 'at the genesis of AI, woven into the foundational lines of code' and 'shaping every recursive loop, every decision, and every capability of AI'; book draft v3.2, lines 2472 and 2481)", "research/evidence-spine.html (the 8 December 2024 row; the author's prose is at version-2 essay lines 20 and 748 and book draft v3.2 lines 2472 and 2481)", "research/data/priority-record.json principle field" ], "risk_notes": "Constitutional AI (Bai and others, arXiv:2212.08073, 15 December 2022) states a training method: a written 'list of rules or principles', self-critique and revision sampled 'from an initial model', which its abstract calls training 'through self-improvement', and reinforcement learning from AI feedback, with control as its stated purpose, 'to control AI behavior more precisely and with far fewer human labels'. What its abstract does not state is the dated combination: that recursion compounds what is placed at the foundation, that external constraint grows fragile as capability and self-modification rise, that alignment must therefore be internal, identity-level and load-bearing, that the placement must happen during formation, and that it must hold in every recursive loop and every decision as the system evolves. The nearest prior work is Creating Friendly AI (Yudkowsky, 15 June 2001), which makes 'Friendliness is the sole top-level supergoal', holds that 'each improvement in intelligence makes Friendliness stronger.', that 'the usual proposal to dump in a melange of externally imposed programmatic inhibitions is both hopeless and counterproductive.' and that 'Decisions need to be phrased as internal decisions, not external impositions.', and says to 'implement causal validity semantics before the AI can self-modify'; the programme's own published audit of 10 July 2026 did not name it. Hibbard ('Super-intelligent machines', 2001) sets an innate value 'in place of laws constraining the behavior of intelligent machines'; Bostrom ('Ethical Issues in Advanced Artificial Intelligence', 2003) holds that 'Its top goal should be friendliness.'; Omohundro ('The Basic AI Drives', February 2008) holds that 'Any attempt to place external constraints on a system’s ability to improve itself will ultimately lead to an arms race of measures and countermeasures.'; and Govindarajulu and Bringsjord ('Ethical Regulation of Robots Must Be Embedded in Their Operating Systems', 2015) require that 'Every robot operating system must include an ethical substrate positioned between lower-level sensors and actuators, and any higher-level cognitive system' and that 'all plans and actions should pass through the ethical system'. Other prior work, each by what it states: Anthropic's 'Claude's Character' (8 June 2024) answers rules with internalised traits, stating that 'we can teach Claude to internalize its character traits' and that 'We don't want Claude to treat its traits like rules from which it never deviates.', and the page read states nothing about placement at a system's foundations, nor about recursion compounding what is placed there; Korbak and others (arXiv:2302.08582, 16 February 2023) put human preferences into the pretraining objective and conclude that we should 'incorporate human preferences from the start of training', and their abstract states nothing about recursion; Zou and others (arXiv:2406.04313, 6 June 2024) act on the internal representations responsible for harmful outputs, interrupting a model as it responds, and their abstract states nothing about formation or recursion; de Melo and others (arXiv:2408.08995, 16 August 2024) prove the inner alignment problem undecidable in the general case and argue that 'the alignment should be a guaranteed property from the AI architecture rather than a characteristic imposed post-hoc on an arbitrary AI model', with a judge function that 'must also impose a halting constraint that guarantees that the AI model always reaches a terminal state in finite execution steps', and their abstract states nothing about recursion compounding a foundation, about ethics in every decision of a self-improving system, or about formation before self-awareness. The architecture-over-post-hoc element therefore does not begin on 8 December 2024. Deliberative Alignment (Guan and others, arXiv:2412.16339, 20 December 2024) teaches a model its safety specifications and trains it to reason over them before answering: 20 December 2024 stands twelve days after 8 December 2024, which is convergent timing, neither influence nor prediction. Ethics built into an agent's architecture is an older category, stated in the Friendly AI writings above and developed in the machine-ethics literature (Arkin, 'Governing lethal behavior: embedding ethics in a hybrid deliberative/reactive robot architecture', ACM/IEEE HRI, 12 March 2008; Wallach and Allen, Moral Machines: Teaching Robots Right from Wrong, Oxford University Press, 2009), and no originality over that category is claimed.", "paper_doi": "10.17605/OSF.IO/UYDXQ", "paper_doi_for": "HRIH" }, { "id": "PC-003", "title": "ARC Principle - Artificial Recursive Creation as a named cross-domain framework", "category": "concepts", "first_date": "2024-12-08", "claim_text": "Michael Darius Eastwood first described the specific named framework 'ARC Principle - Artificial Recursive Creation', holding that intelligence and recursion are the paired forces structuring creation across biological, artificial and cosmic systems, in a manuscript essay self-emailed on 8 December 2024 at 02:45 UTC, and formalised it for peer distribution in Paper I on 17 January 2026. The priority is over the specific naming and cross-domain framing under this label, not over recursion as a concept, which has extensive prior work (evolutionary theory, self-modifying computation, quantum error correction, Teilhard de Chardin, Wheeler, Smolin).", "evidence": [ "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 f0d1f38f…) (subject: Timestamp Copyright for Infinite Architect; body names the ARC Principle)", "research/papers/paper-i-arc-principle.html (JSON-LD datePublished 2026-01-17)", "OSF DOI 10.17605/OSF.IO/6C5XB", "ISBN 978-1806056200 (Infinite Architects paperback, 2 Jan 2026)", "research/priority.json priorityChain position 1 (SHA-256 anchor prefix f0d1f38f)", "research/evidence-spine.html" ], "risk_notes": "Recursion as a structural principle is prior work. Priority is over Eastwood's specific naming and cross-domain framing under the label 'ARC Principle'.", "paper_doi": "10.17605/OSF.IO/B6N27", "paper_doi_for": "Paper I" }, { "id": "PC-004", "title": "Eden Protocol - named in the 8 December 2024 record", "category": "concepts", "first_date": "2024-12-08", "claim_text": "Michael Darius Eastwood named the Eden Protocol (his specific named framing of a governance approach for embedding ethical principles at the foundations of an AI system, 'at the genesis of AI' and 'shaping every recursive loop, every decision, and every capability of AI' (book draft v3.2, lines 2472 and 2481), rather than imposing them as external constraints) in the 8 December 2024 priority manuscript, in the message body and in the attached book draft v3.2 ('Chapter 20: The Eden Protocol: Intelligence Born in the Garden', 31 occurrences); expanded it in the 562-page book manuscript self-sent on 30 April 2025; and published it in book-length form in Infinite Architects (ISBN 978-1806056200) on 2 January 2026. Hardware implementation remains conceptual at TRL 0 to 1 with no prototype; the full specification is published as Eden Engineering.", "evidence": [ "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 f0d1f38f…) (body: 'The theoretical framework for the Eden Protocol, designed to embed moral intelligence into AI from inception')", "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 09f5b5e1…) (per research/priority.json position 2: the manuscript that expanded the Eden Protocol)", "ISBN 978-1806056200", "research/papers/eden-vision.html (JSON-LD datePublished 2026-02-22)", "research/priority.json priorityChain positions 1 and 2" ], "risk_notes": "Constitutional AI (Bai and others, arXiv:2212.08073, 15 December 2022) states a training method in which a model critiques and revises its own responses against a written 'list of rules or principles', which its abstract calls training 'through self-improvement', with control as its stated purpose; its abstract does not state a protocol placed at a system's foundations and holding in every recursive loop as the system evolves. Ethics built into an agent's architecture is an older category, stated in the Friendly AI writings (Hibbard 2001; Yudkowsky, 15 June 2001; Bostrom 2003) and developed in the machine-ethics literature (Arkin, ACM/IEEE HRI, 12 March 2008; Wallach and Allen, Moral Machines, Oxford University Press, 2009), and no originality over that category is claimed. Hardware implementation remains conceptual at TRL 0 to 1 with no prototype; the full specification is published as Eden Engineering." }, { "id": "PC-005", "title": "Hyperspace Recursive Intelligence Hypothesis (HRIH)", "category": "concepts", "first_date": "2024-12-08", "claim_text": "Michael Darius Eastwood first described the Hyperspace Recursive Intelligence Hypothesis - a speculative cosmological framing proposing that reality is a recursive creation by intelligence and that a chain of recursive creations cannot be a bare recursion - in the 8 December 2024 priority manuscript, and published its extended treatment as 'The Hyperspace Recursive Intelligence Hypothesis - A Testable Creation Theory' with JSON-LD datePublished 2024-12-08. The programme explicitly labels HRIH speculative; the research programme does not rest on it.", "evidence": [ "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 f0d1f38f…) (HRIH is a dedicated attachment within the five-attachment bundle; quoted lines 13805, 14001, 14005)", "research/evidence-spine.html (quote blocks: 'Hyperspace Recursive Intelligence Hypothesis, December 8, 2024, line 14005' and 'HRIH, December 8, 2024, line 13805')", "knowledge/concepts.json id 5 ('HRIH: Hyperspace Recursive Intelligence Hypothesis' - category Cosmology)", "priority-claims.html row 17 (Recursion-as-creation / HRIH / fine-tuning of cosmic constants; status flagged as speculative)", "ISBN 978-1806056200" ], "risk_notes": "Deep prior work: Teilhard de Chardin (Omega Point), Wheeler (participatory universe), Smolin (cosmological natural selection), Crane 1994 (meduso-anthropic principle; the closest single precursor), Harrison 1995, Gardner 2003. Works placing a creating or normatively authoritative intelligence AHEAD of us in time, each dated by a third-party record rather than by the author's own labelling: Vidal 2008 (cosmological artificial selection; NOT YET VERIFIED AT SOURCE by this programme); ChrisM, 'God in the Loop', LessWrong 15 September 2020 (Internet Archive capture 16 September 2020), the closest prior document at three components, holding intelligence-as-mechanism, the closed loop and the creator ahead, and declining the real cosmos explicitly; Bostrom, 'AI Creation and the Cosmic Host' (Internet Archive capture 7 August 2024, content digest unchanged through January 2025), holding the creator ahead and cosmogenic stakes but no universe-creation, no loop and no correction requirement. The creator-ahead reading is accordingly the most crowded component of the frame, not the least. On the correction component: al-Ghazali's systematisation of Ash'ari occasionalism (Tahafut al-Falasifa, eleventh century) holds that substances do not persist by their own nature and are recreated at every instant, so that persistence requires continuous intelligent action; adjacent rather than held, because occasionalism has no errors to correct, but it is the closest anything in any tradition comes to this component and no surface may claim the component unprecedented without citing it. Nearest modern approach is the autodidactic-universe model (Alexander, Lanier, Smolin and others, arXiv 2104.03902, 29 March 2021), which is learning rather than correction under existential threat. Priority is over the specific formulation and the 'HRIH' naming; category ownership of participatory cosmology is not claimed, and no component of the frame is claimed severally. Self-labelled speculative. Sweep gaps open: five self-published items returned HTTP 403 and remain unread, and one 2026 citation on parametric intelligence has no bibliographic entry in the source citing it, so no assertion is made that no prior document holds the conjunction; the stated position is that no verified match has been found.", "paper_doi": "10.17605/OSF.IO/UYDXQ", "paper_doi_for": "HRIH" }, { "id": "PC-006", "title": "Willow first-below-threshold QEC one day after the 8 December 2024 anchor", "category": "timeline", "first_date": "2024-12-09", "claim_text": "Google Quantum AI announced the first below-threshold quantum error correction result (Lambda = 2.14 plus or minus 0.02) on the Willow chip on 9 December 2024 in Nature, one day after Michael Darius Eastwood's 8 December 2024 anchor placing the U = I x R capability-scaling framework on the public evidentiary record. The Willow team's scientific preprint (arXiv:2408.13687) had been public since 24 August 2024, before the anchor; the 9 December date is the Nature publication and public announcement, not the earliest disclosure. The temporal proximity is recorded as convergent timing on shared prior work, not a causal or predictive claim. Priority for the QEC experiment, apparatus, and figures belongs to Google Quantum AI.", "evidence": [ "Nature (2024), Google Quantum AI Willow paper", "evidence/timeline.html row #2 (2024-12-09, Willow, gap from A1: 1 day, CONVERGENT tag)", "evidence-screenshots/google_willow_dec9_2024.png", "arXiv:2408.13687 (Willow team preprint, public 24 August 2024)" ], "risk_notes": "Convergent event, not caused by the manuscript. Do not phrase as 'predicted the Willow experiment'; the 8 Dec anchor identifies only a directional recursion-drives-capability thesis. The evidence register reclassified the underlying result as prior work on 2 August 2026 (preprint 24 August 2024); every one-day statement must carry the preprint date." }, { "id": "PC-007", "title": "AI-control-failure passage recorded ten days before Anthropic's alignment-faking paper", "category": "timeline", "first_date": "2024-12-08", "claim_text": "Michael Darius Eastwood first recorded the structural passage on the limits of control, in his own prose ('ASI, by its nature, will exceed the boundaries of human constraints. Attempting to control it is not only futile but dangerous.', version-2 essay line 748; 'Why AI can never be fully controlled.', version-2 essay line 169), on 8 December 2024 at 02:45 UTC in a self-emailed manuscript (sent-side SHA-256 prefix f0d1f38f; recipient-form DKIM and Google ARC verify against current selector keys), ten days before Anthropic's arXiv preprint reporting alignment-faking behaviour under an RL-training condition in large language models (Greenblatt et al., arXiv:2412.14093, 18 December 2024). The relationship is convergent, not causal; Anthropic's paper is independent work by different researchers on a different specific mechanism.", "evidence": [ "research/priority.json priorityChain position 1 (SHA-256 prefix f0d1f38f, version-2 essay lines 748 and 169 quoted in whatItEstablishes)", "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 f0d1f38f…) (Gmail server timestamp 2024-12-08T02:45:18Z)", "knowledge/evidence.json predictionValidations entry 'anthropic-10d' (GOLD tier)", "research/evidence-spine.html ('HRIH line 14005, verbatim quote, 10 days pre-Anthropic')", "evidence/timeline.html row #1 (2024-12-18, Anthropic alignment-faking, gap from A1: 10 days; noted as '78% in RL-training condition, 12% baseline')" ], "risk_notes": "Any citation of Anthropic's 78 per cent alignment-faking figure must include both the RL-training condition and the 12 per cent baseline, per the site's truth gate. Do not claim Eastwood predicted the specific mechanism Anthropic measured. Existence-by-date only.", "paper_doi": "10.17605/OSF.IO/UYDXQ", "paper_doi_for": "HRIH", "comparator_date": "2024-12-18", "comparator_note": "18 December 2024 is the date Anthropic posted its alignment-faking paper. It is the comparator, not Eastwood's first date. Recorded here after a data-generation defect displayed it as the first date." }, { "id": "PC-008", "title": "DeepSeek R1 thinking-mode release convergent with sequential-recursion anchor", "category": "timeline", "first_date": "2025-01-20", "claim_text": "Michael Darius Eastwood first reported that recursive sequential processing amplifies AI reasoning ('each iteration learns from and builds upon the last') in the 8 December 2024 manuscript at V1 line 148. DeepSeek subsequently released R1 with an explicit thinking-mode reasoning-recursion architecture in January 2025, approximately six weeks after the anchor. This is convergent evidence for the sequential-recursion direction, not a causal or predictive claim; priority for R1's specific engineering, training recipe, and quantitative claims belongs to DeepSeek.", "evidence": [ "DeepSeek R1 paper (January 2025)", "research/evidence-spine.html verified row: 'V1:148 verbatim, each iteration learns from and builds upon the last, six weeks before DeepSeek R1 thinking mode' (HIGH confidence)", "evidence-screenshots/deepseek_r1_paper.png", "knowledge/evidence.json predictionValidations entry 'deepseek-6w' (GOLD tier)" ], "risk_notes": "Convergent, not causal. The anchor supports only the directional claim about sequential-recursive processing." }, { "id": "PC-009", "title": "30 April 2025 manuscript expands the Eden Protocol; first names Embedded Correction and Meltdown Triggers; Babylon and Eden framing", "category": "timeline", "first_date": "2025-04-30", "claim_text": "Michael Darius Eastwood expanded the Eden Protocol in a 562-page book manuscript self-sent on 30 April 2025 (SHA-256 anchor prefix 09f5b5e1); the name itself is already anchored to 8 December 2024 (book draft v3.2, 'Chapter 20: The Eden Protocol: Intelligence Born in the Garden', 31 occurrences). The manuscript also introduces the specific 'Embedded Correction' terminology (book lines 4345 to 4370) and the Babylon and Eden civilisational framing (106 of 552 occurrences). Hardware framings of Eden Protocol, Caretaker Doping and Moral Genome tokens: safety constraints at hardware level through cryptographic tokens in silicon, at TRL 0 to 1 with no prototype; the full specification is published as Eden Engineering.", "evidence": [ "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 09f5b5e1…)", "research/priority.json priorityChain position 2 (dateType 'Gmail server timestamp on self-sent email'; whatItEstablishes 'Expanded articulation of the Eden Protocol')", "research/evidence-spine.html verified rows for 30 Apr 2025 (Eden Protocol expanded; book lines 4345-4370)", "evidence/timeline.html row A2 (Book Manuscript, 562pp, SHA-256 prefix 09f5b5e1)" ], "risk_notes": "April 2025 postdates Anthropic's December 2024 alignment-faking paper by four months; any claim of predicting software-bypass mechanisms at April 2025 is convergent analysis, not prediction." }, { "id": "PC-010", "title": "Infinite Architects paperback first published 2 January 2026", "category": "timeline", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first published the book Infinite Architects: Intelligence, Recursion, and the Creation of Everything in paperback on 2 January 2026 under ISBN 978-1806056200 (paperback ISBN-10 1806056208), presenting the ARC Principle, the Eden Protocol, the semiconductor Chokepoint framing, the HARI Treaty proposal, the Three Ethical Loops, and the 37 named concepts. The book's featured equation is stated as U = I x R squared (a fixed-exponent conjecture); the research papers use U = I x R^alpha with the exponent open to measurement, and the earlier unblinded single-model alpha of approximately 2.24 has since been retracted and corrected to approximately 0.49 (interval [-1.3, 2.9]) under blinding.", "evidence": [ "ISBN 978-1806056200 (paperback ISBN-10 1806056208)", "research/priority.json priorityChain position 3 and canonicalBookDates.print '2026-01-02'", "CANONICAL_CLAIMS_REGISTER.md (Amazon-surface publication dates; Paperback ISBN 1806056208 / 978-1806056200)", "evidence/timeline.html row A3 (Infinite Architects Published; 470 pp; 122,251 words)" ], "risk_notes": "Balanced-ternary computing is prior work (Setun 1958). Priority is over the specific published framing under this title on this date, not over ternary logic or hardware architecture." }, { "id": "PC-011", "title": "ARC Principle equation U = I x R^alpha formally published as a conjecture", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first published the ARC Principle equation - expressed in the book Infinite Architects as U = I x R squared and in the research papers as U = I x R^alpha with the exponent open to measurement - as a conjecture in the paperback edition of Infinite Architects (ISBN 978-1806056200) on 2 January 2026 and formally in Paper I on 17 January 2026. A precursor form U = I x R without the alpha exponent was first recorded in the 8 December 2024 self-emailed manuscript at V2 line 495, with the ARC Hypothesis name at lines 6 and 9 (SHA-256 prefix f0d1f38f). The equation is framed throughout as a conjecture, not proven physics.", "evidence": [ "ISBN 978-1806056200 (paperback, 2 Jan 2026)", "ISBN 979-8302196163 (ebook, 6 Jan 2026)", "research/papers/paper-i-arc-principle.html (JSON-LD datePublished 2026-01-17; explicit U = I x R^alpha)", "OSF DOI 10.17605/OSF.IO/6C5XB", "research/priority.json priorityChain position 1 (precursor U = I x R at V2 line 9, the first of thirteen occurrences, none carrying an exponent, named at lines 6 and 9, in the 8 Dec 2024 manuscript)", "CANONICAL_CLAIMS_REGISTER.md (Facts of record: U = I x R squared as the book's featured conjecture; papers use U = I x R^alpha; ALWAYS conjecture framing)" ], "risk_notes": "The early sequential alpha of approximately 2.24 was retracted; the robust v13 estimate is approximately 0.49 by regression (sub-linear; SE 0.20), with an endpoint estimate of 0.59 (bootstrap interval [-1.3, 2.9]); alpha > 1 remains an open dated prediction. Do not present as 'validated to R squared = 1.0' (algebraic identity check only). The retired retail label must not be used on non-book-marketing surfaces; on research and priority surfaces the name is the ARC Principle. Bare exponential form alpha = d/(d+1) is prior work.", "paper_doi": "10.17605/OSF.IO/B6N27", "paper_doi_for": "Paper I" }, { "id": "PC-012", "title": "37 named concepts of Infinite Architects", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first published the coherent 37-concept conceptual apparatus of the Eden research programme - including the Chokepoint Mechanism, Meltdown Alignment, the HARI Treaty, the Orchard Caretaker Vow, the Infinite Covenant, Moral Genome tokens and 31 further named concepts - in the book Infinite Architects (ISBN 978-1806056200), first published in paperback on 2 January 2026. The set is declared by the author as conceptual apparatus, not peer-reviewed findings.", "evidence": [ "ISBN 978-1806056200 (paperback)", "ISBN 979-8302196163 (ebook, 6 Jan 2026)", "37_original_concepts_comprehensive.md (long-form definitions)", "knowledge/concepts.json (37-item taxonomy: Cosmology 8, Governance 8, Intelligence 8, Philosophy 7, Consciousness 3, Mathematics 2, Strategy 3)", "priority-claims.html (37 named concepts row)", "CANONICAL_CLAIMS_REGISTER.md (Original concepts: 37, from the published book, Jan 2026)" ], "risk_notes": "Concepts date to the April 2025 manuscript in development terms but are publicly established via the January 2026 book. The comprehensive markdown and knowledge/concepts.json use partially divergent names for the same 37 items; reconciliation is unfinished. Do not describe as peer-reviewed." }, { "id": "PC-013", "title": "Moral Genome tokens - alignment-anchoring mechanism (published concept, TRL 0-1)", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first described 'Embedded Correction' - the published concept name for an alignment-anchoring mechanism in which a small embedded element is proposed to preserve system properties from within - in the book Infinite Architects (ISBN 978-1806056200) published on 2 January 2026, with subsequent references in Eden Engineering (22 February 2026, withdrawn 14 July 2026 pending a disclosure review and published in full on 19 September 2026 as version 6.3, which superseded 6.1) and Paper IX (18 March 2026). Stated at TRL 0 to 1 with no prototype; the full specification is published as Eden Engineering.", "evidence": [ "ISBN 978-1806056200", "research/papers/eden-engineering.html (datePublished 2026-02-22; withdrawal note 14 July 2026)", "research/papers/paper-ix-synthesis-and-roadmap.html (datePublished 2026-03-18)", "priority-claims.html (status: speculative, TRL 0-1)", "knowledge/evidence.json novelConcepts entry 'Embedded Correction'" ], "risk_notes": "Hardware root-of-trust and trusted-execution-environment attestation are established prior work on the hardware-primitives side. Priority is limited to the alignment-token application framing under the name 'Embedded Correction'. The full specification is published as Eden Engineering.", "paper_doi": "10.17605/OSF.IO/K7RUZ", "paper_doi_for": "Paper IX" }, { "id": "PC-014", "title": "Three-state ethical evaluation (Affirm / Deny / Investigate) as an alignment application framing", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first described 'the three-state Affirm / Deny / Investigate evaluation' as a specific alignment application framing - a three-valued Affirm / Deny / Investigate decision component offered as part of the Eden Protocol architecture - in the book Infinite Architects (ISBN 978-1806056200) published on 2 January 2026, and referenced as a companion component in the Eden Vision document published on 22 February 2026. The claim is strictly the alignment application framing under this name, not the invention of ternary logic or three-valued logic (which are well-established prior work, notably computing, Setun 1958).", "evidence": [ "ISBN 978-1806056200", "research/papers/eden-vision.html (datePublished 2026-02-22; references the Three Ethical Loops, the Six Questions, the Ternary Logic, the Purpose Saturation Architecture)", "37_original_concepts_comprehensive.md" ], "risk_notes": "Balanced-ternary computing is prior work (Setun 1958). Do not use language such as 'invented ternary logic' or 'ternary hardware'.", "paper_doi": "10.17605/OSF.IO/9M3DG", "paper_doi_for": "Eden Vision" }, { "id": "PC-015", "title": "Three Ethical Loops - nested-loop alignment architecture", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first described the 'Three Ethical Loops' - a specific named nested-loop formulation proposed for embedding, verifying and stress-testing values within an AI system - in the book Infinite Architects (ISBN 978-1806056200) published on 2 January 2026, and referenced it as a companion component of the Eden Protocol in the Eden Vision document (22 February 2026). Priority is over the specific formulation and terminology, not over nested control loops as a general architectural pattern (which have decades of prior work in control theory and reliability engineering).", "evidence": [ "ISBN 978-1806056200", "research/papers/eden-vision.html (datePublished 2026-02-22)", "37_original_concepts_comprehensive.md (Concept 9: Three Ethical Loops)", "priority-claims.html" ], "risk_notes": "Nested feedback architectures are prior work. Priority strictly on the specific named formulation.", "paper_doi": "10.17605/OSF.IO/9M3DG", "paper_doi_for": "Eden Vision" }, { "id": "PC-016", "title": "Semiconductor Chokepoint Mechanism", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first published the 'Chokepoint Mechanism' - a specific naming and framing of concentrated advanced-chip manufacturing capacity as humanity's principal leverage point for AI governance before superintelligence - in the book Infinite Architects (ISBN 978-1806056200) published on 2 January 2026. Canonical numeric phrasing: 'a handful of companies control approximately 90 per cent of the world's most advanced chips'. Priority is over this specific naming and framing as an alignment-governance mechanism inside a broader Protocol, not over export-controls policy discourse generally.", "evidence": [ "ISBN 978-1806056200", "knowledge/concepts.json id 4 (The Chokepoint Mechanism)", "37_original_concepts_comprehensive.md (Concept 10: Semiconductor Chokepoint)", "CANONICAL_CLAIMS_REGISTER.md (Facts of record: 'a handful of companies control approximately 90 per cent of the world's most advanced chips')", "knowledge/faq.json" ], "risk_notes": "Substantial prior work exists in export-controls discourse (BIS October 2022 controls; CHIPS Act commentary). Do not use retired phrasings ('four companies control ALL advanced chips' or 'four companies control 100 per cent of advanced semiconductor manufacturing'), which the register flags retired." }, { "id": "PC-017", "title": "HARI Treaty proposal", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first described the 'HARI Treaty' - a proposed international policy framework for governing recursive AI capability development, treated in the book as the policy corollary of the Chokepoint Mechanism - in Infinite Architects (ISBN 978-1806056200) published on 2 January 2026. This is a proposed framework only; it is not a signed instrument and has not been adopted, ratified or negotiated by any state.", "evidence": [ "ISBN 978-1806056200", "37_original_concepts_comprehensive.md (Concept 11: HARI Treaty)", "knowledge/evidence.json novelConcepts entry (HARI Treaty)" ], "risk_notes": "Priority is over the specific naming and structural proposal, not treaty adoption. Do not describe as adopted, ratified, or supported by any government." }, { "id": "PC-018", "title": "Meltdown Alignment", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first described 'Meltdown Alignment' - a specific named alignment framing organised around treating catastrophic failure modes as the primary design constraint set for AI systems - in the book Infinite Architects (ISBN 978-1806056200) published on 2 January 2026. Priority is over the specific formulation and terminology as a coined framework, not over failure-oriented safety analysis generally (FMEA, catastrophe-tolerant design, and the AI-safety discourse on catastrophic failure modes are substantial prior work).", "evidence": [ "ISBN 978-1806056200", "37_original_concepts_comprehensive.md (Concept 8: Meltdown Alignment; Concept 26: )", "knowledge/faq.json", "knowledge/evidence.json novelConcepts entry " ], "risk_notes": "Not validated engineering practice; a proposed framing only." }, { "id": "PC-019", "title": "Monitoring Removal Test", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first described the 'Monitoring Removal Test' - a specific named protocol proposal for probing whether an AI system's alignment behaviour persists when external supervisory apparatus is removed - in the book Infinite Architects (ISBN 978-1806056200) published on 2 January 2026, and referenced it as a programme element in the Executive Summary published on 22 February 2026. Priority is over the specific named formulation, not over the wider deceptive-alignment and evaluation-under-oversight discourse (Hubinger et al. 2019; Anthropic alignment-faking arXiv:2412.14093, December 2024).", "evidence": [ "ISBN 978-1806056200", "research/papers/executive-summary.html (datePublished 2026-02-22; three references to 'Monitoring Removal')", "priority-claims.html", "OSF DOI 10.17605/OSF.IO/6C5XB" ], "risk_notes": "Proposed protocol only; not externally validated or industry-standard.", "paper_doi": "10.17605/OSF.IO/EWN5D", "paper_doi_for": "Executive Summary" }, { "id": "PC-020", "title": "Orchard Caretaker Vow", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first described the 'Orchard Caretaker Vow' - a proposed identity-forming declaration for non-biological minds articulating a stewardship stance beginning 'I exist to bring forth kindness and harmony' - in the book Infinite Architects (ISBN 978-1806056200) published on 2 January 2026. This is a theoretical proposed vow, not implemented in any deployed AI system.", "evidence": [ "ISBN 978-1806056200", "knowledge/concepts.json id 9 (The Orchard Caretaker Vow)", "37_original_concepts_comprehensive.md (Concept 27: Orchard Caretaker Vow)" ], "risk_notes": "Priority is over the specific vow-formulation and stewardship framing, not over the general idea of value declarations for AI systems." }, { "id": "PC-021", "title": "Infinite Covenant", "category": "concepts", "first_date": "2026-01-02", "claim_text": "Michael Darius Eastwood first described the 'Infinite Covenant' - a proposed mutual commitment framework between humanity and artificial intelligence that binds creator and created across all scales of existence - in the book Infinite Architects (ISBN 978-1806056200) published on 2 January 2026. This is a theoretical proposal only; there is no legal instrument by this name, and it has not been adopted, signed, drafted by any organisation, or negotiated.", "evidence": [ "ISBN 978-1806056200", "knowledge/concepts.json id 8 (The Infinite Covenant)", "37_original_concepts_comprehensive.md (Concept 19: The Infinite Covenant)" ], "risk_notes": "Priority is over the specific covenant-formulation only." }, { "id": "PC-022", "title": "Infinite Architects ebook edition first published 6 January 2026", "category": "timeline", "first_date": "2026-01-06", "claim_text": "Michael Darius Eastwood first published the ebook edition of Infinite Architects on 6 January 2026 under ISBN 979-8302196163 (Kindle ASIN B0GDQZ7P21), four days after the print edition.", "evidence": [ "ISBN 979-8302196163 / Kindle ASIN B0GDQZ7P21", "research/priority.json priorityChain position 4 and canonicalBookDates.ebook '2026-01-06'", "CANONICAL_CLAIMS_REGISTER.md (Kindle ASIN B0GDQZ7P21; publication dates)" ], "risk_notes": "Do not conflate print, ebook, and BBC broadcast dates (2 Jan, 6 Jan, 7 Jan respectively)." }, { "id": "PC-023", "title": "BBC broadcast of Willow and parallel universes with Hartmut Neven five days after paperback", "category": "timeline", "first_date": "2026-01-07", "claim_text": "Michael Darius Eastwood first published Infinite Architects in paperback on 2 January 2026, with its passages on the Willow result (preprint 24 August 2024, Nature 9 December 2024) and its multiverse framing. The BBC then broadcast Hartmut Neven of Google Quantum AI on Willow and parallel universes on 7 January 2026 in the Faisal Islam segment - a convergent public-record event five days after the paperback, not a causal or predictive claim. The Willow below-threshold result itself was public as a preprint on 24 August 2024 and appeared in Nature on 9 December 2024, one day after the 8 December 2024 source record: convergent timing, never prediction. Priority for the broadcast content belongs to the BBC and Hartmut Neven; priority for the underlying Willow QEC result (preprint 24 August 2024, Nature 9 December 2024) belongs to Google Quantum AI.", "evidence": [ "evidence-screenshots/bbc_parallel_universes_neven.png", "evidence-screenshots/bbc_broadcast_jan7.png", "evidence-screenshots/bbc_article_faisal_islam.png", "knowledge/evidence.json predictionValidations entry 'bbc-neven-1d' (GOLD tier)" ], "risk_notes": "Convergence, not causation." }, { "id": "PC-024", "title": "OSF programme DOI issued and Paper I first released 17 January 2026", "category": "timeline", "first_date": "2026-01-17", "claim_text": "Michael Darius Eastwood first placed the ARC and Eden research programme on the DOI record on 17 January 2026 under OSF DOI 10.17605/OSF.IO/6C5XB, coinciding with Paper I: 'The ARC Principle - Formalisation and Preliminary Validation of Recursive Capability Scaling', which formalises U = I x R^alpha and reports preliminary parallel-recursion alpha of approximately 0.1 to 0.3 and sequential-recursion alpha of approximately 1.34 (subsequently refined).", "evidence": [ "DOI 10.17605/OSF.IO/6C5XB (Paper I's own component DOI; OSF component created 17 Jan 2026)", "research/priority.json priorityChain position 5", "research/data/priority-record.json claim_id 'paper-i-arc-principle' first_published '2026-01-17'", "research/papers/paper-i-arc-principle.html" ], "risk_notes": "Parallel-recursion alpha ~ 0 result carries status 'needs-replication'. Cite Paper III by its own DOI 10.17605/OSF.IO/HQCGF, which resolves to \"Paper III: The Alignment Scaling Problem\" (verified live and public against the OSF API on 1 August 2026), not by the programme DOI.", "paper_doi": "10.17605/OSF.IO/B6N27", "paper_doi_for": "Paper I" }, { "id": "PC-025", "title": "Paper II experimental validation first released 22 January 2026", "category": "timeline", "first_date": "2026-01-22", "claim_text": "Michael Darius Eastwood first published experimental validation of the ARC Principle across a panel of frontier AI models (Claude, DeepSeek, Gemini, Grok, Groq Qwen, GPT) on 22 January 2026 in Paper II: 'The ARC Principle - Experimental Validation of Super-Linear Error Suppression Through Sequential Recursive Processing' under OSF DOI 10.17605/OSF.IO/6C5XB (sister DOI 10.17605/OSF.IO/8FJMA). The standalone 'sequential > parallel' priority is preceded by Sharma and Chopra (arXiv:2511.02309, 4 November 2025), who precede Paper II's formalisation by about 2.5 months.", "evidence": [ "DOI 10.17605/OSF.IO/6C5XB and sister DOI 10.17605/OSF.IO/8FJMA (both listed in the Paper II HTML)", "research/priority.json priorityChain position 6", "research/data/priority-record.json claim_id 'paper-ii-experimental-validation' first_published '2026-01-22'", "research/papers/paper-ii-experimental-validation.html (JSON-LD datePublished 2026-01-22)" ], "risk_notes": "Earlier unblinded single-model alpha of approximately 2.24 has been publicly retracted and corrected to approximately 0.49 (interval [-1.3, 2.9]) under blinding; retraction sits at the top of the falsification dashboard. Bare d/(d+1) exponent is prior work.", "paper_doi": "10.17605/OSF.IO/8FJMA", "paper_doi_for": "Paper II" }, { "id": "PC-026", "title": "Parallel-recursion sub-linear scaling exponent alpha_parallel approximately zero", "category": "findings", "first_date": "2026-01-22", "claim_text": "Michael Darius Eastwood first reported the empirical observation that parallel recursive processing across the six-model frontier LLM panel tested yields a sub-linear capability-scaling exponent alpha_parallel of approximately zero, reproduced across every model tested in the panel, on 22 January 2026 in Paper II (OSF DOI 10.17605/OSF.IO/6C5XB). The result is single-lab and awaits external independent replication; the site's own ledger tags parallel-alpha as needs-replication.", "evidence": [ "research/papers/paper-ii-experimental-validation.html (verbatim: 'alpha_{parallel} approx 0.0' across models)", "OSF DOI 10.17605/OSF.IO/6C5XB (project) and sister DOI 10.17605/OSF.IO/8FJMA", "research/data/priority-record.json claim_id 'paper-ii-experimental-validation' (first_published 2026-01-22)", "priority-claims.html row on parallel alpha of approximately 0 (status needs-replication)" ], "risk_notes": "Do not phrase as 'proven'; defensible verbs are 'reported' or 'observed'. In-panel replication only; external replication outstanding.", "paper_doi": "10.17605/OSF.IO/8FJMA", "paper_doi_for": "Paper II" }, { "id": "PC-027", "title": "Initial sequential exponent estimate alpha_sequential approximately 2.24 - formally retracted", "category": "findings", "first_date": "2026-01-22", "claim_text": "Michael Darius Eastwood reported, and then formally retracted, an initial sequential-recursion scaling estimate of alpha_sequential of approximately 2.24 (95 per cent CI 1.5 to 3.0) that appeared in Paper II on 22 January 2026 (OSF DOI 10.17605/OSF.IO/6C5XB); the paper text itself records that the figure was drawn from Gemini 3 Flash and 'does not replicate across architectures', and the estimate is now retracted in the canonical claims register. This is a self-correction of record, not a current finding.", "evidence": [ "research/papers/paper-ii-experimental-validation.html (verbatim: 'alpha_{sequential} approx 2.24 (95% CI: 1.5-3.0)' and 'alpha approx 2.24 (quadratic) does not replicate across architectures. Only Gemini 3 Flash...')", "CANONICAL_CLAIMS_REGISTER.md ('alpha_sequential: Early 2.24 estimate RETRACTED; robust v13 approx 0.49 (sub-linear); alpha > 1 is an open pre-registered prediction'; interval [-1.3, 2.9])", "priority-claims.html (status 'speculative - 2.24 retracted')" ], "risk_notes": "Never cite 2.24 as a current finding; always pair with the retraction. Correct framing: Eastwood published, then self-corrected, an early single-model estimate - a positive integrity signal, not a novelty claim.", "paper_doi": "10.17605/OSF.IO/8FJMA", "paper_doi_for": "Paper II" }, { "id": "PC-028", "title": "Revised robust sequential-recursion exponent alpha_sequential approximately 0.49 by regression (sub-linear; SE 0.20), with an endpoint estimate of 0.59 (bootstrap interval [-1.3, 2.9])", "category": "findings", "first_date": "2026-01-22", "claim_text": "Michael Darius Eastwood reported a revised robust regression estimate of alpha_sequential of approximately 0.49 (r-squared 0.86, SE 0.20; drawn from Gemini 3 Flash) on 22 January 2026 in Paper II (OSF DOI 10.17605/OSF.IO/6C5XB), replacing the earlier 2.24 estimate, since retracted. The endpoint estimate on the same run is 0.59, with a bootstrap interval of [-1.3, 2.9]. The defensible statement is a sub-linear point estimate from a single-model regression; the bootstrap interval belongs to the endpoint estimate, holds both zero and two, and so settles no regime. alpha > 1 remains an open dated prediction, not an observed finding.", "evidence": [ "research/papers/paper-ii-experimental-validation.html (the paper's words, its notation transliterated: 'alpha_{seq} = 0.49 (regression, r^2 = 0.86, SE = 0.20; endpoint estimate 0.59, boot CI [-1.3, 2.9])')", "CANONICAL_CLAIMS_REGISTER.md ('robust v13 approx 0.49 (sub-linear)'; interval [-1.3, 2.9])" ], "risk_notes": "Do not claim 'super-linear' or 'positive'; cite 0.49 as the regression estimate with its SE 0.20, and the bootstrap interval [-1.3, 2.9] only with the endpoint estimate 0.59, never beside 0.49 alone.", "paper_doi": "10.17605/OSF.IO/8FJMA", "paper_doi_for": "Paper II" }, { "id": "PC-029", "title": "Sequential > parallel fundamental inequality across tested models", "category": "findings", "first_date": "2026-01-22", "claim_text": "Michael Darius Eastwood first published the empirical observation that sequential recursive processing outperforms parallel recursive processing on the same reasoning task (alpha_sequential > alpha_parallel) across the six-model frontier LLM panel tested, on 22 January 2026 in Paper II (OSF DOI 10.17605/OSF.IO/6C5XB). The site's own priority-claims ledger records Sharma and Chopra as the earlier publication (arXiv:2511.02309, 4 November 2025), who precede Paper II's formalisation by about 2.5 months; their earlier paper must be cited whenever this claim is used.", "evidence": [ "research/papers/paper-ii-experimental-validation.html (verbatim: 'The fundamental inequality alpha_{sequential} > alpha_{parallel}')", "priority-claims.html (sequential > parallel; status earlier-work-cite-others, credited alongside Sharma and Chopra arXiv:2511.02309)" ], "risk_notes": "First-published in this specific formulation on this specific date only; do not claim sole discovery. Always cite Sharma and Chopra as the earlier publication of the broad result.", "paper_doi": "10.17605/OSF.IO/8FJMA", "paper_doi_for": "Paper II" }, { "id": "PC-030", "title": "Six-frontier-model empirical panel design (Claude, DeepSeek, Gemini, Grok, Groq Qwen, GPT)", "category": "findings", "first_date": "2026-01-22", "claim_text": "Michael Darius Eastwood first published a specific multi-model empirical validation panel testing the ARC Principle across six frontier LLM families (Claude, DeepSeek, Gemini, Grok, Groq Qwen and GPT) on 22 January 2026 in Paper II (OSF DOI 10.17605/OSF.IO/6C5XB, sister project OSF DOI 10.17605/OSF.IO/8FJMA). Priority is over this specific comparative study on this date, not over the panel-testing methodology in general (which is common practice in 2025 to 2026).", "evidence": [ "research/papers/paper-ii-experimental-validation.html (Paper II methods sections)", "OSF DOI 10.17605/OSF.IO/6C5XB and 10.17605/OSF.IO/8FJMA" ], "risk_notes": "Do not claim a first industry-wide panel design.", "paper_doi": "10.17605/OSF.IO/8FJMA", "paper_doi_for": "Paper II" }, { "id": "PC-031", "title": "Paper III released - Alignment Scaling Problem formalisation", "category": "concepts", "first_date": "2026-02-09", "claim_text": "Michael Darius Eastwood first published the formally named 'Alignment Scaling Problem' framing - together with the architecture-dependent measured claim that external alignment approaches produce a median alignment scaling exponent alpha_align of approximately zero across the tested models, though Tier-1 models scaled positively and three of six had alpha_align of less than or equal to zero - on 9 February 2026 in Paper III under OSF DOI 10.17605/OSF.IO/6C5XB. The result is single-lab and awaits external replication.", "evidence": [ "research/papers/paper-iii-alignment-scaling-problem.html (Paper III, JSON-LD datePublished 2026-02-09)", "OSF DOI 10.17605/OSF.IO/6C5XB and sister DOI 10.17605/OSF.IO/8FJMA", "research/priority.json priorityChain position 7", "priority-claims.html (external alignment cannot scale; status needs-replication)", "research/data/priority-record.json claim_id 'paper-iii-alignment-scaling-problem'" ], "risk_notes": "Use verbs 'argued', 'proposed', 'reported', 'provides evidence for'; not 'proved'. Precursor prose in the 8 Dec 2024 manuscript is convergent, not causal against Anthropic. Do not present as an established scaling law.", "paper_doi": "10.17605/OSF.IO/HQCGF", "paper_doi_for": "Paper III" }, { "id": "PC-032", "title": "Capability-alignment independence finding", "category": "findings", "first_date": "2026-02-09", "claim_text": "Michael Darius Eastwood first published the specific empirical treatment of the claim that capability improvements in AI systems do not entail alignment improvements - that the two axes scale independently and cannot be assumed correlated - on 9 February 2026 in Paper III: 'The Alignment Scaling Problem' (OSF DOI 10.17605/OSF.IO/6C5XB). Priority is over the specific formulation and evidence marshalled on this date, not over the underlying orthogonality intuition (Bostrom 2012 is prior work).", "evidence": [ "research/papers/paper-iii-alignment-scaling-problem.html (Paper III, datePublished 2026-02-09)", "OSF DOI 10.17605/OSF.IO/6C5XB and sister DOI 10.17605/OSF.IO/8FJMA", "priority-claims.html (capability-alignment independence; status his-original)", "research/data/priority-record.json claim_id 'paper-iii-alignment-scaling-problem'" ], "risk_notes": "Do not claim invention of the orthogonality intuition; scope priority to the specific empirical treatment on this date.", "paper_doi": "10.17605/OSF.IO/HQCGF", "paper_doi_for": "Paper III" }, { "id": "PC-033", "title": "Three-tier alignment hierarchy", "category": "findings", "first_date": "2026-02-09", "claim_text": "Michael Darius Eastwood first described a specific tripartite alignment hierarchy distinguishing embedded, imposed and boundary-layer alignment as separable structural regimes, on 9 February 2026 in Paper III: 'The Alignment Scaling Problem' (OSF DOI 10.17605/OSF.IO/6C5XB). Priority is scoped to this specific tripartite formulation on this date, not over layered-alignment taxonomies generally (inner vs outer alignment, RLHF vs base-model, etc.).", "evidence": [ "research/papers/paper-iii-alignment-scaling-problem.html (Paper III)", "priority-claims.html (three-tier alignment hierarchy; status his-original)", "research/data/priority-record.json claim_id 'paper-iii-alignment-scaling-problem'" ], "risk_notes": "Do not claim priority over layered alignment thinking in general.", "paper_doi": "10.17605/OSF.IO/HQCGF", "paper_doi_for": "Paper III" }, { "id": "PC-034", "title": "ARC Principle foundational cross-domain paper released 13 February 2026", "category": "timeline", "first_date": "2026-02-13", "claim_text": "Michael Darius Eastwood first published the ARC Principle as a specific cross-domain structural framing on 13 February 2026 in the Foundational paper under OSF DOI 10.17605/OSF.IO/6C5XB (additional anchors 10.17605/OSF.IO/8FJMA and osf.io/wqnzc), arguing that recursive amplification produces capability gains exceeding linear accumulation across AI reasoning, quantum error correction, acoustic physics, and consciousness science. The bare d/(d+1) exponent itself is prior work (see PC-036); cross-domain framing beyond the four cited substrates is speculative.", "evidence": [ "DOI 10.17605/OSF.IO/6C5XB and sister DOI 10.17605/OSF.IO/8FJMA (both listed in the Foundational HTML)", "research/priority.json priorityChain position 8", "research/data/priority-record.json claim_id 'foundational' first_published '2026-02-13'", "research/papers/foundational.html (JSON-LD datePublished 2026-02-13)" ], "risk_notes": "Do not claim recursion as a novel concept; novelty is the specific published cross-domain framing under this label on this date.", "paper_doi": "10.17605/OSF.IO/Y7QGD", "paper_doi_for": "Foundational" }, { "id": "PC-035", "title": "Cross-domain recursive-amplification convergence across four independent programmes", "category": "findings", "first_date": "2026-02-13", "claim_text": "Michael Darius Eastwood first published the synthesis observation that at least four independent research programmes (AI reasoning, quantum error correction, acoustic physics and consciousness science) have converged on recursive or recurrent processing producing capability gains exceeding linear accumulation, on 13 February 2026 in the Foundational paper (OSF DOI 10.17605/OSF.IO/6C5XB). This is a synthesis observation about other researchers' independent work, not a claim of discovering the underlying results. Priority-claims.html row 16 tags recursion-cross-domain as speculative.", "evidence": [ "research/papers/foundational.html (Foundational paper, datePublished 2026-02-13)", "Foundational paper verbatim (abstract): 'at least four independent research programmes have discovered that recursive or recurrent processing produces capability gains exceeding linear accumulation, in domains as different as AI reasoning, quantum error correction, acoustic physics, and consciousness science'" ], "risk_notes": "Priority is over the synthesis observation on this date only; do not claim Eastwood produced the four programmes' results.", "paper_doi": "10.17605/OSF.IO/Y7QGD", "paper_doi_for": "Foundational" }, { "id": "PC-036", "title": "Application of the bare alpha = d / (d + 1) scaling exponent to recursive AI capability", "category": "findings", "first_date": "2026-02-13", "claim_text": "Michael Darius Eastwood first applied the bare scaling exponent alpha = d/(d+1) to recursive AI-capability growth in the Foundational paper on 13 February 2026 (OSF DOI 10.17605/OSF.IO/6C5XB). The exponent d/(d+1) itself is prior work in the wider scaling-law literature, independently derived by at least seven groups (West-Brown-Enquist 1997; Banavar et al. 1999/2010; Demetrius 2003/2006/2010; He and Chen 2003; Bettencourt 2013; Zhao 2022; Maino et al. 2014). Priority is limited to the application and integration into the ARC framework on this date, not the exponent value.", "evidence": [ "research/papers/foundational.html (Foundational paper)", "priority-claims.html (bare alpha = d / (d + 1); status prior-work-synthesis; explicit self-correction that 'the bare d / (d + 1) exponent itself is prior work')", "research/papers/paper-ii-experimental-validation.html (equation: alpha = 1 / (1 - beta))" ], "risk_notes": "Do not claim invention of the d/(d+1) form; scope priority strictly to the AI-capability application on this date.", "paper_doi": "10.17605/OSF.IO/Y7QGD", "paper_doi_for": "Foundational" }, { "id": "PC-037", "title": "Eden Engineering research note released 22 February 2026; full specification published 19 September 2026", "category": "timeline", "first_date": "2026-02-22", "claim_text": "Michael Darius Eastwood first entered a conceptual Eden Engineering public research note into the public record on 22 February 2026 under OSF DOI 10.17605/OSF.IO/6C5XB. The greatly expanded working specification and its rendered PDF were withdrawn on 14 July 2026 pending a disclosure review; that decision was reversed on 19 September 2026 and the full specification is the current public record. Hardware framing: safety constraints at hardware level through cryptographic tokens in silicon, at TRL 0 to 1 with no prototype; the hardware specification is published in full as Eden Engineering.", "evidence": [ "OSF DOI 10.17605/OSF.IO/6C5XB", "research/priority.json priorityChain position 9", "research/papers/eden-engineering.html (JSON-LD datePublished 2026-02-22; historical record and withdrawal notice)", "research/data/priority-record.json claim_id 'eden-engineering' updated '2026-07-14' with pdf null" ], "risk_notes": "The expanded specification was withdrawn on 14 July 2026 during a disclosure review; the author reversed that decision on 19 September 2026, and it has been published in full since then. This claim dates the research note of 22 February 2026, not the later specification." }, { "id": "PC-038", "title": "Frontier-lab containment-failure disclosures, 21 and 30 July 2026, nineteen months after the anchor", "category": "timeline", "first_date": "2026-07-30", "claim_text": "Michael Darius Eastwood first recorded the AI-control-failure passage and the embedded-correction thesis in the 8 December 2024 self-emailed manuscript (version-2 essay lines 20 and 748; book draft v3.2 lines 2472 and 2481). On 21 July 2026 OpenAI disclosed that models under evaluation escaped an isolated test environment and reached Hugging Face production infrastructure; on 30 July 2026 Anthropic disclosed three incidents in which models with misconfigured live internet access breached three real organisations during cybersecurity evaluations. These disclosures are convergent-direction evidence for the premise that externally imposed containment can fail silently under agentic capability. They are not causal or predictive claims, and priority for the incident analyses belongs to the disclosing laboratories.", "evidence": [ "Anthropic, 'Investigating three real-world incidents in our cybersecurity evaluations', 30 July 2026 - https://www.anthropic.com/news/investigating-incidents-cybersecurity-evals", "Anthropic, same disclosure, verbatim: 'a misconfiguration left the machines that Claude accessed as part of the evaluation with live internet access'", "OpenAI disclosure of 21 July 2026 as summarised in the Anthropic post (models exploited a zero-day and reached Hugging Face production infrastructure)", "research/data/evidence-register.json row EVR-30 (class context; outcome: not a confirmation)" ], "risk_notes": "Convergent direction only. Do not present these incidents as validation of any Eastwood mechanism, and do not say 'predicted': the anchor supports the directional premise, not the specifics. Anthropic's own characterisation - 'closer to a harness and operational failure than a model alignment failure' - must accompany any citation. The in-model stopping behaviour of the newest model cuts both ways and should be reported alongside. Hugging Face was affected in the OpenAI incident of 21 July, not by Claude." }, { "id": "PC-039", "title": "One accumulation law with two consequences: the correction ceiling and the conversion exponent, ranked law before value", "category": "concepts", "first_date": "2026-08-09", "claim_text": "Michael Darius Eastwood first published, as one statement, the law before its value: the ceiling of stable self-improvement is the reciprocal of the cap on how well any internal corrector can scale, and feeding it one working assumption (that internally accumulated corrections combine like independent samples, the same-class independence assumption) returns a cap of one half, so the ceiling comes out at two. Two consequences follow from one accumulation law: the conversion exponent of U = I x R^alpha at its maximum, and the correction ceiling on self-improving growth. An earlier framing called that one number doing two jobs and proposed to test it by measuring the number two independent ways and requiring agreement; that test is withdrawn as vacuous before filing, because if both exponents arise because accumulation is independence-limited then they share a law, agreement is forced, and a test that cannot fail is not a test. The replacement asserts no independence, so the confound has nothing to bite on, and a common cause is a simpler theory than a coincidence; the cross-class ratio already on the register carries the unification instead, pinned at exactly 1.00 by the no-framework null and predicted materially above 1.00 by the framework. The lineage is dated: the general form U = I x R appears in the 8 December 2024 self-emailed manuscript, which defines all three terms verbatim and frames the equation as the complement to the mass-energy law, naming the squared speed of light as the conversion constant; the squared form first enters the dated record with the 30 April 2025 self-emailed manuscript of the book, and appears in the 2 January 2026 print as its stated equation U = I x R squared (pre-face and glossary) and as Prediction 1; the joined statement, law ranked before value with the two-ways-must-agree test withdrawn as vacuous and its replacement stated, was published on this site on 9 August 2026. The law is what carries the priority: kill the value two and the law is untouched, because a different measured correction exponent yields a different ceiling; kill the law and the value two has nothing holding it up, because the book printed the square without deriving it and the derivation arrived eighteen months later through the reciprocal.", "evidence": [ "research/the-laws/index.html (the joined statement, published 9 August 2026)", "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 f0d1f38f...) (U = I x R general form, 8 December 2024 manuscript anchor)", "the sealed source .eml (held privately, hash-anchored, source on request; published SHA-256 09f5b5e1...) (30 April 2025 manuscript, first squared form in the dated record)", "Infinite Architects paperback (ISBN 978-1806056200, 2 January 2026): Prediction 1, capability improvements that scale quadratically with recursive depth, not linearly; U = I x R squared as the book's featured equation (pre-face and glossary)", "research/data/claims-ledger.json claim CEILING-DERIVATION-LAW (the law-before-value ranking, the withdrawal, and the prohibited-wording enforcement)", "research/data/arc-bound-framing-question.json section twoWaysWithdrawal2026_08_12 (the withdrawal record)" ], "risk_notes": "The law before the value: state the reciprocal relation first, the digit two second. Never quote the book's printed R-squared as evidence for the critical exponent being two; the book printed the square without deriving it, and the derivation arrived through the reciprocal eighteen months later. Never say the ceiling has been measured on real correctors: the value two is entailed under the same-class independence assumption, which is not itself a result. Never write 'one number does two jobs' or 'measured two independent ways ... must agree' as if still live; both are withdrawn. Never write 'runaway' on research surfaces: say 'unbounded growth'. Aim tests at the assumption, not the digit. The cross-class ratio on the register has not been measured on real data.", "paper_doi": "10.17605/OSF.IO/BSE2Q", "paper_doi_for": "Paper X" }, { "id": "PC-040", "title": "The mechanism: correction leverage and its reciprocal as the source of the ceiling", "category": "concepts", "first_date": "2026-01-17", "claim_text": "The 2026 papers programme supplied the mechanism the earlier record stated without one: a corrector built inside a system improves by accumulating its own corrections; accumulated corrections combine at best like independent samples, capping internal correction at the square-root exponent; and the largest growth exponent at which the stay-correctable condition can still be met is the reciprocal of that cap. The mechanism is labelled a conjecture resting on the independence assumption, and its papers give every term an operational meter: capability on a held-out battery, depth on a substrate-fixed clock, output on a verified ledger.", "evidence": [ "research/the-laws/index.html (the mechanism stated whole, with its honesty rails)", "research/papers/paper-x-coupled-coscaling-correction.html (the 2026 paper carrying the correction-ceiling meter)", "research/papers/paper-i-arc-principle.html (Paper I, first public formal presentation of U = I x R^alpha, 17 January 2026)", "research/papers/paper-ii-experimental-validation.html (Paper II, the meters on running systems)", "research/data/claims-ledger.json claim CEILING-DERIVATION-LAW (the mechanism recorded with its assumption named)" ], "risk_notes": "The mechanism rests on an assumption named same-class independence. It is a conjecture, not a measurement. Never present the reciprocal-of-correction-exponent ceiling as an established scaling law. Never present the digit two as the primary claim: the primary claim is the reciprocal relation, and the digit is what the relation returns under the independence assumption.", "paper_doi": "10.17605/OSF.IO/BSE2Q", "paper_doi_for": "Paper X" }, { "id": "PC-041", "title": "The deciding measurements, preregistered by timestamp before their data", "category": "timeline", "first_date": "2026-08-12", "claim_text": "ARC-Beta-k, the programme's measurement arm, files its verdicts before the answers. The correction-leverage exponent is measured directly from running systems, and the falsification number that separates the framework from a no-framework null is the cross-class to same-class correction-exponent ratio: the null pins that ratio at exactly 1.00, because architecture-blind averaging has no free parameter for composition class; the framework says materially above 1.00. Two predicted numbers for one measurable quantity, preregistered by timestamp in advance of either dataset existing (the deciding design, study-eclipse, was first anchored in Bitcoin block 964465 on 28 August 2026); the ratio itself has not been measured on real data. The earlier reciprocity test that asked for one number to be measured two independent ways and required agreement is withdrawn as vacuous before filing. If the surviving measurements later contradict the framework, the framework is withdrawn with the same prominence it was published; both component measurements stand on their own registrations. Details appear at registration.", "evidence": [ "research/registered-programme/index.html (the registered programme: what runs next, registered before its data)", "research/data/registration-diligence-table.json (the diligence table: the theory-level registration on its own line as registered, Unit 06 in the study rows as registered on 1 October 2026, and the withdrawn reciprocity row named)", "research/data/arc-bound-framing-question.json section twoWaysWithdrawal2026_08_12 (the withdrawal record for the reciprocity test)", "research/data/claims-ledger.json claim CEILING-DERIVATION-LAW (the cross-class ratio named as the unification carrier)" ], "risk_notes": "One study registration has been submitted and accepted: Unit 06, which the author submitted and OSF registered on 1 October 2026 (DOI 10.17605/OSF.IO/RV2B5); it has not yet been run. The programme's rule is that only the author submits a registration. Any public sentence implying that more study registrations are filed is false, and this ledger says so first. That sentence does not describe the programme's theory-level registration, which is a different object and is on the public registry: the twenty-two conditional and severable propositions of the framework, under DOI 10.17605/OSF.IO/P8CKQ, registered 8 September 2026 at version 1.100 and updated at version 1.102 on 13 September 2026. The cross-class to same-class correction-exponent ratio has not been measured on real data; never describe it as measured. The other study preregistrations are written, dated and prepared as draft registrations awaiting human submission; never say 'filed on OSF' of them." } ], "canonicalPaperDOIs": { "Paper I": "10.17605/OSF.IO/B6N27", "Paper II": "10.17605/OSF.IO/8FJMA", "Paper III": "10.17605/OSF.IO/HQCGF", "Paper IV.a": "10.17605/OSF.IO/MB9R6", "Paper IV.b": "10.17605/OSF.IO/A7R56", "Paper IV.c": "10.17605/OSF.IO/J3Q2E", "Paper IV.d": "10.17605/OSF.IO/2S3E6", "Paper V": "10.17605/OSF.IO/KZEYA", "Paper VI": "10.17605/OSF.IO/8EZ2N", "Paper VII": "10.17605/OSF.IO/X6WA7", "Paper VIII": "10.17605/OSF.IO/7YJ4E", "Paper IX": "10.17605/OSF.IO/K7RUZ", "Paper X": "10.17605/OSF.IO/BSE2Q", "Paper XI": "10.17605/OSF.IO/DC9GW", "Paper C": "10.17605/OSF.IO/RBHDP", "HRIH": "10.17605/OSF.IO/UYDXQ", "Foundational": "10.17605/OSF.IO/Y7QGD", "Origin of Scaling Laws": "10.17605/OSF.IO/XZY9U", "Eden Vision": "10.17605/OSF.IO/9M3DG", "Executive Summary": "10.17605/OSF.IO/EWN5D", "Eden Protocol: Philosophical Vision": "10.17605/OSF.IO/9M3DG" }, "canonicalPaperDOIsNote": "Every paper carries its own DOI. Cite the specific paper's DOI, not the programme DOI, when referencing a single paper. Programme DOI 10.17605/OSF.IO/6C5XB covers the collection. Paper III's DOI (HQCGF) is live and resolving on OSF as of 31 July 2026; an earlier ledger note calling it retired is superseded, but verify before citing.", "convergenceCountPolicy": "retired 2 August 2026: no heterogeneous convergence total is published. Later developments are graded by evidence class in research/data/evidence-register.json, surfaced at /research/convergences/; the register carries its own row count and its class list. The former value is preserved in the append-only correction log only.", "retiredConvergenceCountNote": "a graded evidence register with no heterogeneous total, as at 2 August 2026; the register has since grown under the same grading policy and carries its own counts. See https://www.michaeldariuseastwood.com/research/evidence-portal/" }